Background Screening for suicidal ideation in high-risk groups such as U.S. veterans is crucial for early detection and suicide prevention. Currently, screening is based on clinical interviews or self-report measures. Both approaches rely on subjects to disclose their suicidal thoughts. Innovative approaches are necessary to develop objective and clinically applicable assessments. Speech has been investigated as an objective marker to understand various mental states including suicidal ideation. In this work, we developed a machine learning and natural language processing classifier based on speech markers to screen for suicidal ideation in US veterans. Methodology Veterans submitted 588 narrative audio recordings via a mobile app in a real-life setting. In addition, participants completed self-report psychiatric scales and questionnaires. Recordings were analyzed to extract voice characteristics including prosodic, phonation, and glottal. The audios were also transcribed to extract textual features for linguistic analysis. We evaluated the acoustic and linguistic features using both statistical significance and ensemble feature selection. We also examined the performance of different machine learning algorithms on multiple combinations of features to classify suicidal and non-suicidal audios. Results A combined set of 15 acoustic and linguistic features of speech were identified by the ensemble feature selection. Random Forest classifier, using the selected set of features, correctly identified suicidal ideation in veterans with 86% sensitivity, 70% specificity, and an area under the receiver operating characteristic curve (AUC) of 80%. Conclusions Speech analysis of audios collected from veterans in everyday life settings using smartphones offers a promising approach for suicidal ideation detection. A machine learning classifier may eventually help clinicians identify and monitor high-risk veterans.
This is the first study to extend AS findings to PTSD and suggests a specific capability to measure inhibitory control using eye-tracking technology. We discuss the notion that reduced capacity to regulate facial-related processing affects cognitive and attentional control networks of PTSD patients, potentially representing a core cognitive deficit.
Veterans of all war eras have a high rate of chronic disease, mental health disorders, and chronic multi-symptom illnesses (CMI).1-3 Many veterans report symptoms that affect multiple biological systems as opposed to isolated disease states. Standard medical treatments often target isolated disease states such as headaches, insomnia, or back pain and at times may miss the more complex, multisystem dysfunction that has been documented in the veteran population. Research has shown that veterans have complex symptomatology involving physical, cognitive, psychological, and behavioral disturbances, such as difficult to diagnose pain patterns, irritable bowel syndrome, chronic fatigue, anxiety, depression, sleep disturbance, or neurocognitive dysfunction.2-4 Meditation and acupuncture are each broad-spectrum treatments designed to target multiple biological systems simultaneously, and thus, may be well suited for these complex chronic illnesses. The emerging literature indicates that complementary and integrative medicine (CIM) approaches augment standard medical treatments to enhance positive outcomes for those with chronic disease, mental health disorders, and CMI.5-12
Objective: A subset of military veterans who have experienced both traumatic brain injury and psychological trauma present with chronic neuropsychiatric symptoms and experience persistent obstacles to social reintegration. This project aimed to develop a novel treatment targeting the unmet social rehabilitation needs of these veterans. Initial intervention development, feasibility, and outcome data are explored. Method: Four treatment groups were conducted (n ϭ 20). A treatment workbook was developed during Groups 1 and 2 (n ϭ 10) and research data were collected from Groups 3 and 4 (n ϭ 10). Results: There was a 0% attrition rate across all groups with unanimous requests for additional sessions. T test effect sizes were analyzed with bias-corrected Hedges' g. Improvements were observed on measures of depression (p ϭ .026, g ϭ 0.73), empathic perspective taking (p ϭ .007, g ϭ 0.94), social cognition (p ϭ .002-.678, g ϭ 0.27-1.30 across multiple measures), social relationships (p ϭ .007, g ϭ 1.50), traumatic brain injury-related quality of life (social: p ϭ .014, g ϭ 0.68, emotional: p ϭ .009, g ϭ 1.28) and nonsocial executive functioning (p ϭ .006, g ϭ 0.54). Conclusions and Implications for Practice: Preliminary evidence from this exploratory study suggests that targeting multiple layers of social competence using a combined psychotherapy and cognitive rehabilitation approach holds promise. Larger, controlled studies are needed to further evaluate the feasibility and efficacy of this intervention. Impact and ImplicationsThis study demonstrates that a yearlong social rehabilitation group for veterans with chronic neuropsychiatric symptoms following traumatic brain injury and psychological trauma may possibly result in improved social cognition, social participation, mood, and quality of life. Our preliminary findings highlight the importance of focusing on chronic care needs in polytrauma to optimize functioning and prevent further deterioration. This intervention targets co-occurring neuropsychiatric conditions simultaneously, rather than focusing on one condition at a time, to serve individuals who tend to fall outside of the scope of existing treatments.
Trait anger may have a more deleterious effect on relationship functioning than PTSD symptoms. Theoretical and clinical implications are discussed.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.